Edit a sent message

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare a non-read-only, open-world, non-idempotent, non-destructive operation, and the description adds meaningful context beyond that: the recipient sees the edit, there is a hard 15-minute window, and edits are capped at 5. What is missing is failure behavior (what error or result occurs past the window/limit) and whether prior edits are replaced.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, with the core action first and the constraints and social consequence immediately after. Every clause conveys operational information; nothing is padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter mutation with no output schema, the description supplies the constraints and side effects an agent needs to decide and act correctly. Only the failure/limit-exceeded behavior and explicit parameter naming are absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for two parameters, so the description must carry the load. It implies text is the replacement content and that message_id must reference a message the caller sent, which is genuinely useful, but it never names or defines either parameter and gives no format guidance for the message identifier.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Change the text of an iMessage you sent') and adds the defining scope: only messages you sent, within 15 minutes, up to 5 times. This is clearly distinguishable from sending or unsending a message without needing to inspect any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The eligibility window (15 minutes) and edit limit (5 times) tell the agent when this tool is applicable and implicitly when it is not, since an older message or a sixth attempt cannot use it. It does not explicitly name a fallback such as unsend_message or send_message, so an alternative route for expired messages is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.